Automated Gleason Grading of Prostate Biopsies using Deep Learning
This work addresses the need for more consistent and accurate prostate cancer prognostics for patients and clinicians, representing a strong domain-specific advancement rather than an incremental improvement.
The authors tackled the problem of inter-observer variability in Gleason grading for prostate cancer by developing a fully automated deep learning system using 5834 biopsies from 1243 patients, which achieved high agreement with a reference standard and outperformed 10 out of 15 pathologists in an observer experiment.
The Gleason score is the most important prognostic marker for prostate cancer patients but suffers from significant inter-observer variability. We developed a fully automated deep learning system to grade prostate biopsies. The system was developed using 5834 biopsies from 1243 patients. A semi-automatic labeling technique was used to circumvent the need for full manual annotation by pathologists. The developed system achieved a high agreement with the reference standard. In a separate observer experiment, the deep learning system outperformed 10 out of 15 pathologists. The system has the potential to improve prostate cancer prognostics by acting as a first or second reader.